Applying artificial intelligence technology to assist with breast cancer diagnosis and prognosis prediction

A Multi-label Artificial Intelligence Approach for Improving Breast Cancer Detection With Mammographic Image Analysis

BACKGROUND/AIM

Breast cancer remains a major global health concern. This study aimed to develop a deep-learning-based artificial intelligence (AI) model that predicts the malignancy of mammographic lesions and reduces unnecessary biopsies in patients with breast cancer.

PATIENTS AND METHODS

In this retrospective study, we used deep-learning-based AI to predict whether lesions in mammographic images are malignant. The AI model learned the malignancy as well as margins and shapes of mass lesions through multi-label training, similar to the diagnostic process of a radiologist. We used the Curated Breast Imaging Subset of Digital Database for Screening Mammography. This dataset includes annotations for mass lesions, and we developed an algorithm to determine the exact location of the lesions for accurate classification. A multi-label classification approach enabled the model to recognize malignancy and lesion attributes.

RESULTS

Our multi-label classification model, trained on both lesion shape and margin, demonstrated superior performance compared with models trained solely on malignancy. Gradient-weighted class activation mapping analysis revealed that by considering the margin and shape, the model assigned higher importance to border areas and analyzed pixels more uniformly when classifying malignant lesions. This approach improved diagnostic accuracy, particularly in challenging cases, such as American College of Radiology Breast Imaging-Reporting and Data System categories 3 and 4, where the breast density exceeded 50%.

CONCLUSION

This study highlights the potential of AI in improving the diagnosis of breast cancer. By integrating advanced techniques and modern neural network designs, we developed an AI model with enhanced accuracy for mammographic image analysis.

The potential benefit of artificial intelligence regarding clinical decision-making in the treatment of wrist trauma patients

PURPOSE

The implementation of artificial intelligence (AI) in health care is gaining popularity. Many publications describe powerful AI-enabled algorithms. Yet there's only scarce evidence for measurable value in terms of patient outcomes, clinical decision-making or socio-economic impact. Our aim was to investigate the significance of AI in the emergency treatment of wrist trauma patients.

METHOD

Two groups of physicians were confronted with twenty realistic cases of wrist trauma patients and had to find the correct diagnosis and provide a treatment recommendation. One group was assisted by an AI-enabled application which detects and localizes distal radius fractures (DRF) with near-to-perfect precision while the other group had no help. Primary outcome measurement was diagnostic accuracy. Secondary outcome measurements were required time, number of added CT scans and senior consultations, correctness of the treatment, subjective and objective stress levels.

RESULTS

The AI-supported group was able to make a diagnosis without support (no additional CT, no senior consultation) in significantly more of the cases than the control group (75% vs. 52%, p = 0.003). The AI-enhanced group detected DRF with superior sensitivity (1.00 vs. 0.96, p = 0.06) and specificity (0.99 vs. 0.93, p = 0.17), used significantly less additional CT scans to reach the correct diagnosis (14% vs. 28%, p = 0.02) and was subjectively significantly less stressed (p = 0.05).

CONCLUSION

The results indicate that physicians can diagnose wrist trauma more accurately and faster when aided by an AI-tool that lessens the need for extra diagnostic procedures. The AI-tool also seems to lower physicians' stress levels while examining cases. We anticipate that these benefits will be amplified in larger studies as skepticism towards the new technology diminishes.

Develop and Validate a Nomogram Combining Contrast-Enhanced Spectral Mammography Deep Learning with Clinical-Pathological Features to Predict Neoadjuvant Chemotherapy Response in Patients with ER-Positive/HER2-Negative Breast Cancer

RATIONALE AND OBJECTIVES

To develop and validate a nomogram that combines contrast-enhanced spectral mammography (CESM) deep learning with clinical-pathological features to predict neoadjuvant chemotherapy (NAC) response (either low Miller Payne (MP-L) grades 1-2 or high MP (MP-H) grades 3-5) in patients with ER-positive/HER2-negative breast cancer.

MATERIALS AND METHODS

In this retrospective study, 265 breast cancer patients were randomly allocated into training and test sets (used for models training and testing, respectively) at a 4:1 ratio. Deep learning models, based on the pre-trained ResNet34 model and initially fine-tuned for identifying breast cancer, were trained using low-energy and subtracted CESM images. The predicted results served as deep learning features for the deep learning-based model. Clinical-pathological features, including age, progesterone receptor (PR) status, estrogen receptor (ER) status, Ki67 expression levels, and neutrophil-to-lymphocyte ratio, were used for the clinical model. All these features contributed to the nomogram. Feature selection was performed through univariate analysis. Logistic regression models were developed and chosen using a stepwise selection method. The deep learning-based and clinical models, along with the nomogram, were evaluated using precision-recall curves, receiver operating characteristic (ROC) curves, specificity, recall, accuracy, negative predictive value, positive predictive value (PPV), balanced accuracy, F1-score, and decision curve analysis (DCA).

RESULTS

The nomogram demonstrated considerable predictive ability, with higher area under the ROC curve (0.95, P < 0.05), accuracy (0.94), specificity (0.98), PPV (0.89), and precision (0.89) compared to the deep learning-based and clinical models. In DCA, the nomogram showed substantial clinical value in assisting breast cancer treatment decisions, exhibiting a higher net benefit than the other models.

CONCLUSION

The nomogram, integrating CESM deep learning with clinical-pathological features, proved valuable for predicting NAC response in patients with ER-positive/HER2-negative breast cancer. Nomogram outperformed deep learning-based and clinical models.

Artificial intelligence-based computer-aided diagnosis abnormality score trends in the serial mammography of patients with breast cancer

PURPOSE

To explore the abnormality score trends of artificial intelligence-based computer-aided diagnosis (AI-CAD) in the serial mammography of patients until a final diagnosis of breast cancer.

METHOD

From 2015 to 2019, 126 breast cancer patients who had at least two previous mammograms obtained from 2008 up to cancer diagnosis were included. AI-CAD was retrospectively applied to 487 previous mammograms and all the abnormality scores calculated by AI-CAD were obtained. The contralateral breast of each affected breast was defined as the control group. We divided all mammograms by 6-month intervals from cancer diagnosis in reverse chronological order. The random coefficient model was used to estimate whether the chronological trend of AI-CAD abnormality scores differed between cancer and normal breasts. Subgroup analyses were performed according to mammographic visibility, invasiveness and molecular subtype of the invasive cancer.

RESULTS

Mean period from initial examination to cancer diagnosis was 6.0 years (range 1.7-10.7 years). The abnormality scores of breasts diagnosed with cancer showed a significantly increasing trend during the previous examination period (slope 0.6 per 6 months, p for the slope < 0.001), while the contralateral normal breast showed no trend (slope 0.03, p = 0.776). The difference in slope between the cancerous and contralateral breasts was significant (p < 0.001). For mammography-visible cancers, the abnormality scores in cancerous breasts showed a significant increasing trend (slope 0.8, p < 0.001), while for mammography-occult cancers, the trend was not significant (slope 0.1, p = 0.6). For invasive cancers, the slope of the abnormality scores showed a significant increasing trend (slope 1.4, p = 0.002), unlike ductal carcinoma in situ (DCIS) which showed no significant trend. There was no significant difference in the slope of abnormality scores among the subtypes of invasive cancers (p = 0.418).

CONCLUSION

Breasts diagnosed with cancer showed an increase in AI-CAD abnormality scores in previous serial mammograms, suggesting that AI-CAD could be useful for early detection of breast cancer.

Automatic detection and visualization of temporomandibular joint effusion with deep neural network

This study investigated the usefulness of deep learning-based automatic detection of temporomandibular joint (TMJ) effusion using magnetic resonance imaging (MRI) in patients with temporomandibular disorder and whether the diagnostic accuracy of the model improved when patients' clinical information was provided in addition to MRI images. The sagittal MR images of 2948 TMJs were collected from 1017 women and 457 men (mean age 37.19 ± 18.64 years). The TMJ effusion diagnostic performances of three convolutional neural networks (scratch, fine-tuning, and freeze schemes) were compared with those of human experts based on areas under the curve (AUCs) and diagnosis accuracies. The fine-tuning model with proton density (PD) images showed acceptable prediction performance (AUC = 0.7895), and the from-scratch (0.6193) and freeze (0.6149) models showed lower performances (p < 0.05). The fine-tuning model had excellent specificity compared to the human experts (87.25% vs. 58.17%). However, the human experts were superior in sensitivity (80.00% vs. 57.43%) (all p < 0.001). In gradient-weighted class activation mapping (Grad-CAM) visualizations, the fine-tuning scheme focused more on effusion than on other structures of the TMJ, and the sparsity was higher than that of the from-scratch scheme (82.40% vs. 49.83%, p < 0.05). The Grad-CAM visualizations agreed with the model learned through important features in the TMJ area, particularly around the articular disc. Two fine-tuning models on PD and T2-weighted images showed that the diagnostic performance did not improve compared with using PD alone (p < 0.05). Diverse AUCs were observed across each group when the patients were divided according to age (0.7083-0.8375) and sex (male:0.7576, female:0.7083). The prediction accuracy of the ensemble model was higher than that of the human experts when all the data were used (74.21% vs. 67.71%, p < 0.05). A deep neural network (DNN) was developed to process multimodal data, including MRI and patient clinical data. Analysis of four age groups with the DNN model showed that the 41-60 age group had the best performance (AUC = 0.8258). The fine-tuning model and DNN were optimal for judging TMJ effusion and may be used to prevent true negative cases and aid in human diagnostic performance. Assistive automated diagnostic methods have the potential to increase clinicians' diagnostic accuracy.

Bibliometric analysis of phosphoglycerate kinase 1 expression in breast cancer and its distinct upregulation in triple-negative breast cancer

BACKGROUND

Phosphoglycerate kinase 1 (PGK1) has been identified as a possible biomarker for breast cancer (BC) and may play a role in the development and advancement of triple-negative BC (TNBC).

AIM

To explore the PGK1 and BC research status and PGK1 expression and mechanism differences among TNBC, non-TNBC, and normal breast tissue.

METHODS

PGK1 and BC related literature was downloaded from Web of Science Core Collection Core Collection. Publication counts, key-word frequency, cooperation networks, and theme trends were analyzed. Normal breast, TNBC, and non-TNBC mRNA data were gathered, and differentially expressed genes obtained. Area under the summary receiver operating characteristic curves, sensitivity and specificity of PGK1 expression were determined. Kaplan Meier revealed PGK1's prognostic implication. PGK1 co-expressed genes were explored, and Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, and Disease Ontology applied. Protein-protein interaction networks were constructed. Hub genes identified.

RESULTS

PGK1 and BC related publications have surged since 2020, with China leading the way. The most frequent keyword was "Expression". Collaborative networks were found among co-citations, countries, institutions, and authors. PGK1 expression and BC progression were research hotspots, and PGK1 expression and BC survival were research frontiers. In 16 TNBC vs non-cancerous breast and 15 TNBC vs non-TNBC datasets, PGK1 mRNA levels were higher in 1159 TNBC than 1205 non-cancerous breast cases [standardized mean differences (SMD): 0.85, 95% confidence interval (95%CI): 0.54-1.16, I² = 86%, P < 0.001]. PGK1 expression was higher in 1520 TNBC than 7072 non-TNBC cases (SMD: 0.25, 95%CI: 0.03-0.47, I² = 91%, P = 0.02). Recurrence free survival was lower in PGK1-high-expression than PGK1-low-expression group (hazard ratio: 1.282, P = 0.023). PGK1 co-expressed genes were concentrated in ATP metabolic process, HIF-1 signaling, and glycolysis/gluconeogenesis pathways.

CONCLUSION

PGK1 expression is a research hotspot and frontier direction in the BC field. PGK1 may play a strong role in promoting cancer in TNBC by mediating metabolism and HIF-1 signaling pathways.

Breast Cancer Screening Using Inverse Modeling of Surface Temperatures and Steady-State Thermal Imaging

Cancer is characterized by increased metabolic activity and vascularity, leading to temperature changes in cancerous tissues compared to normal cells. This study focused on patients with abnormal mammogram findings or a clinical suspicion of breast cancer, exclusively those confirmed by biopsy. Utilizing an ultra-high sensitivity thermal camera and prone patient positioning, we measured surface temperatures integrated with an inverse modeling technique based on heat transfer principles to predict malignant breast lesions. Involving 25 breast tumors, our technique accurately predicted all tumors, with maximum errors below 5 mm in size and less than 1 cm in tumor location. Predictive efficacy was unaffected by tumor size, location, or breast density, with no aberrant predictions in the contralateral normal breast. Infrared temperature profiles and inverse modeling using both techniques successfully predicted breast cancer, highlighting its potential in breast cancer screening.

An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies

The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.

Invasive Lobular Carcinoma: A Review of Imaging Modalities with Special Focus on Pathology Concordance

Invasive lobular cancer (ILC) is the second most common type of breast cancer. It is characterized by a unique growth pattern making it difficult to detect on conventional breast imaging. ILC can be multicentric, multifocal, and bilateral, with a high likelihood of incomplete excision after breast-conserving surgery. We reviewed the conventional as well as newly emerging imaging modalities for detecting and determining the extent of ILC- and compared the main advantages of MRI vs. contrast-enhanced mammogram (CEM). Our review of the literature finds that MRI and CEM clearly surpass conventional breast imaging in terms of sensitivity, specificity, ipsilateral and contralateral cancer detection, concordance, and estimation of tumor size for ILC. Both MRI and CEM have each been shown to enhance surgical outcomes in patients with newly diagnosed ILC that had one of these imaging modalities added to their preoperative workup.

Automated Quantification of Pneumonia Infected Volume in Lung CT Images: A Comparison with Subjective Assessment of Radiologists

OBJECTIVE

To help improve radiologists' efficacy of disease diagnosis in reading computed tomography (CT) images, this study aims to investigate the feasibility of applying a modified deep learning (DL) method as a new strategy to automatically segment disease-infected regions and predict disease severity.

METHODS

We employed a public dataset acquired from 20 COVID-19 patients, which includes manually annotated lung and infections masks, to train a new ensembled DL model that combines five customized residual attention U-Net models to segment disease infected regions followed by a Feature Pyramid Network model to predict disease severity stage. To test the potential clinical utility of the new DL model, we conducted an observer comparison study. First, we collected another set of CT images acquired from 80 COVID-19 patients and process images using the new DL model. Second, we asked two chest radiologists to read images of each CT scan and report the estimated percentage of the disease-infected lung volume and disease severity level. Third, we also asked radiologists to rate acceptance of DL model-generated segmentation results using a 5-scale rating method.

RESULTS

Data analysis results show that agreement of disease severity classification between the DL model and radiologists is >90% in 45 testing cases. Furthermore, >73% of cases received a high rating score (≥4) from two radiologists.

CONCLUSION

This study demonstrates the feasibility of developing a new DL model to automatically segment disease-infected regions and quantitatively predict disease severity, which may help avoid tedious effort and inter-reader variability in subjective assessment of disease severity in future clinical practice.

Role of artificial intelligence in risk prediction, prognostication, and therapy response assessment in colorectal cancer: current state and future directions

Artificial Intelligence (AI) is a branch of computer science that utilizes optimization, probabilistic and statistical approaches to analyze and make predictions based on a vast amount of data. In recent years, AI has revolutionized the field of oncology and spearheaded novel approaches in the management of various cancers, including colorectal cancer (CRC). Notably, the applications of AI to diagnose, prognosticate, and predict response to therapy in CRC, is gaining traction and proving to be promising. There have also been several advancements in AI technologies to help predict metastases in CRC and in Computer-Aided Detection (CAD) Systems to improve miss rates for colorectal neoplasia. This article provides a comprehensive review of the role of AI in predicting risk, prognosis, and response to therapies among patients with CRC.

Improving Performance of Breast Lesion Classification Using a ResNet50 Model Optimized with a Novel Attention Mechanism

Background: The accurate classification between malignant and benign breast lesions detected on mammograms is a crucial but difficult challenge for reducing false-positive recall rates and improving the efficacy of breast cancer screening. Objective: This study aims to optimize a new deep transfer learning model by implementing a novel attention mechanism in order to improve the accuracy of breast lesion classification. Methods: ResNet50 is selected as the base model to develop a new deep transfer learning model. To enhance the accuracy of breast lesion classification, we propose adding a convolutional block attention module (CBAM) to the standard ResNet50 model and optimizing a new model for this task. We assembled a large dataset with 4280 mammograms depicting suspicious soft-tissue mass-type lesions. A region of interest (ROI) is extracted from each image based on lesion center. Among them, 2480 and 1800 ROIs depict verified benign and malignant lesions, respectively. The image dataset is randomly split into two subsets with a ratio of 9:1 five times to train and test two ResNet50 models with and without using CBAM. Results: Using the area under ROC curve (AUC) as an evaluation index, the new CBAM-based ResNet50 model yields AUC = 0.866 ± 0.015, which is significantly higher than that obtained by the standard ResNet50 model (AUC = 0.772 ± 0.008) (p < 0.01). Conclusion: This study demonstrates that although deep transfer learning technology attracted broad research interest in medical-imaging informatic fields, adding a new attention mechanism to optimize deep transfer learning models for specific application tasks can play an important role in further improving model performances.